A Theoretical Framework for Understanding and Building "Any-task inference" Capable Foundation Models
In this work, we provide a formal framework and mathematical definition for the subset of foundation models focused on enabling the property of "any-task inference" (ATI) (similar to zero-shot inference), rather than those designed for pre-training fine-tuning.
By Matthew McDermott, Florent Pollet, Payal Chandak, Gregory Kondas, Liat Friedman Antwarg, Noa Dagan, Isaac KohanearXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Nov 2, 2026.
Comments
Sign in to join the discussion.